Robust Face Recognition Against Eyeglasses Interference by Integrating Local and Global Facial Features
In this paper, we proposed a feature extraction method to solve a challenge problem of face recognition, i.e., recognition of faces with eyeglasses. By fusing the local and global facial features, the proposed method can extract robust facial features that can greatly reduce the negative influence of eyeglasses on face recognition. Firstly, we use the Ununiformed Local Gabor Binary Pattern Histogram Sequence (ULGBPHS) method to extract local facial features. Secondly, we apply 2D-Discrete Fourier Transform (2D-DFT) method to obtain global facial features. Finally, we use a weighted fusion strategy to combine the two kinds of facial features for face recognition. Extensive experimental results on the well-known public GT and CMU_PIE face datasets, and real scene dataset which is built by our group show that the proposed feature extraction method obtains the best performance among some state-of-the-art methods. The relevant code and data will be available at http://www.yongxu.org/lunwen.html.
KeywordsFace recognition Eyeglasses Local and global facial features
This paper is partially supported by Guangdong Province high-level personnel of special support program (No. 2016TX03X164) and Shenzhen Fundamental Research fund (JCYJ20160331185006518).
- 4.Deng, Y., Guo, Z., Chen, Y.: Fusing local patterns of gabor and non-subsampled contourlet transform for face recognition. In: IAPR Asian Conference on Pattern Recognition, pp. 481–485 (2013)Google Scholar
- 5.Givens, G., Beveridge, J.R., Draper, B.A., Grother, P., Phillips, P.J.: How features of the human face affect recognition: a statistical comparison of three face recognition algorithms. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 381–389 (2004)Google Scholar
- 8.Heo, J., Kong, S.G., Abidi, B.R., Abidi, M.A.: Fusion of visual and thermal signatures with eyeglass removal for robust face recognition. In: Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 2004, p. 122 (2004)Google Scholar
- 10.Liu, L., Sun, Y., Yin, B., Song, C.: A novel nonuniform division strategy for wearing eyeglasses face recognition. In: Fifth International Conference on Image and Graphics, pp. 907–911 (2009)Google Scholar
- 12.Nefian, A.: Georgia tech face database (2013), http://www.anefian.com/research/face_reco.html
- 15.Solanki, K., Pittalia, P.: Review of face recognition techniques. Int. J. Comput. Appl. 133, 20–24 (2016)Google Scholar
- 18.Yang, P., Shan, S., Gao, W., Li, S.Z., Zhang, D.: Face recognition using Ada-boosted gabor features. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, pp. 356–361 (2004)Google Scholar
- 19.Yi, D., Li, S.Z.: Learning sparse feature for eyeglasses problem in face recognition. In: 2011 IEEE International Conference on Automatic Face & Gesture Recognition and Workshops (FG 2011), pp. 430–435. IEEE (2011)Google Scholar
- 21.Zanchettin, C.: Face recognition based on global and local features. In: Proceedings of the 29th Annual ACM Symposium on Applied Computing, pp. 55–57. ACM (2014)Google Scholar
- 23.Zhang, W., Shan, S., Gao, W., Chen, X., Zhang, H.: Local gabor binary pattern histogram sequence (LGBPHS): a novel non-statistical model for face representation and recognition. In: Tenth IEEE International Conference on Computer Vision, pp. 786–791 Vol. 1 (2005)Google Scholar
- 24.Zhao, W., Chellappa, R., Phillips, P.J., Rosenfeld, A.: Face recognition: a literature survey. ACM Comput. Surv. 35(4), 399–458 (2003), http://doi.acm.org/10.1145/954339.954342